From a340847b0214aa9b8fd9839f7b2822ccc607edab Mon Sep 17 00:00:00 2001 From: Victor Zhao Date: Thu, 13 Oct 2022 11:06:33 +0800 Subject: Revert "drm/amdgpu: let mode2 reset fallback to default when failure" This reverts commit dac6b80818ac2353631c5a33d140d8d5508e2957. This commit reverted the AMDGPU_SKIP_MODE2_RESET as it conflicts with the original design of reset handler. Will redesign it. Fixes: dac6b80818ac23 ("drm/amdgpu: let mode2 reset fallback to default when failure") Signed-off-by: Victor Zhao Reviewed-by: Lijo Lazar Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c | 1 - 1 file changed, 1 deletion(-) (limited to 'drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c') diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c index 2dad7aa9a03b..75f1402101f4 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c @@ -1950,7 +1950,6 @@ static void amdgpu_ras_do_recovery(struct work_struct *work) reset_context.method = AMD_RESET_METHOD_NONE; reset_context.reset_req_dev = adev; clear_bit(AMDGPU_NEED_FULL_RESET, &reset_context.flags); - clear_bit(AMDGPU_SKIP_MODE2_RESET, &reset_context.flags); amdgpu_device_gpu_recover(ras->adev, NULL, &reset_context); } -- cgit From 001ebcf5b903646b40697d9b1dc9b24daae82b4f Mon Sep 17 00:00:00 2001 From: YiPeng Chai Date: Tue, 27 Sep 2022 14:06:42 +0800 Subject: drm/amdgpu: Enable ras support for mp0 v13_0_0 and v13_0_10 V1: Enable ras support for CHIP_IP_DISCOVERY asic type. V2: 1. Change commit comment. 2. Enable ras support for mp0 v13_0_0 and v13_0_10. Signed-off-by: YiPeng Chai Reviewed-by: Hawking Zhang Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c') diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c index 75f1402101f4..4a8f73cc4cb5 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c @@ -2267,6 +2267,16 @@ static int amdgpu_ras_recovery_fini(struct amdgpu_device *adev) static bool amdgpu_ras_asic_supported(struct amdgpu_device *adev) { + if (adev->asic_type == CHIP_IP_DISCOVERY) { + switch (adev->ip_versions[MP0_HWIP][0]) { + case IP_VERSION(13, 0, 0): + case IP_VERSION(13, 0, 10): + return true; + default: + return false; + } + } + return adev->asic_type == CHIP_VEGA10 || adev->asic_type == CHIP_VEGA20 || adev->asic_type == CHIP_ARCTURUS || -- cgit From 3bd026c3e3317e4490595848261fe74d76e74126 Mon Sep 17 00:00:00 2001 From: YiPeng Chai Date: Wed, 28 Sep 2022 15:52:02 +0800 Subject: drm/amdgpu: Add sriov vf ras support in amdgpu_ras_asic_supported V2: Add sriov vf ras support in amdgpu_ras_asic_supported. Signed-off-by: YiPeng Chai Reviewed-by: Hawking Zhang Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c | 14 +++++++++----- 1 file changed, 9 insertions(+), 5 deletions(-) (limited to 'drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c') diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c index 4a8f73cc4cb5..a4b47e1bd111 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c @@ -2267,6 +2267,15 @@ static int amdgpu_ras_recovery_fini(struct amdgpu_device *adev) static bool amdgpu_ras_asic_supported(struct amdgpu_device *adev) { + if (amdgpu_sriov_vf(adev)) { + switch (adev->ip_versions[MP0_HWIP][0]) { + case IP_VERSION(13, 0, 2): + return true; + default: + return false; + } + } + if (adev->asic_type == CHIP_IP_DISCOVERY) { switch (adev->ip_versions[MP0_HWIP][0]) { case IP_VERSION(13, 0, 0): @@ -2320,11 +2329,6 @@ static void amdgpu_ras_check_supported(struct amdgpu_device *adev) !amdgpu_ras_asic_supported(adev)) return; - /* If driver run on sriov guest side, only enable ras for aldebaran */ - if (amdgpu_sriov_vf(adev) && - adev->ip_versions[MP1_HWIP][0] != IP_VERSION(13, 0, 2)) - return; - if (!adev->gmc.xgmi.connected_to_cpu) { if (amdgpu_atomfirmware_mem_ecc_supported(adev)) { dev_info(adev->dev, "MEM ECC is active.\n"); -- cgit